DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This office action is a response to an amendment filed 02/27/2026, with a request for continued examination filed 02/27/2026.
Claims 1-20 are pending.
Claims 1, 4, 14, 16, 18, and 20 are amended.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 02/27/2026 has been entered.
Response to Arguments
Applicant’s arguments, filed 02/27/2026, have been fully considered but are moot in view of the new grounds of rejection. Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Rejections based on a newly cited reference(s) follow.
Examiner Notes
Examiner cites particular columns and line numbers in the references as applied to the claims below for the convenience of the applicant. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested that, in preparing responses, the applicant fully consider the references in entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the examiner.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 2, 12, 14, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over US Patent Publication No. 2022/0058497 to Vazquez-Canteli et al., (hereinafter Vazquez), in view of US Patent Publication No. 2022/0100851 to Mehrotra et al., (hereinafter Mehrotra).
Regarding claim 1, Vazquez teaches a building system of a building (Building automation system of a building, see Abs, p104, Vazquez), the building system comprising:
one or more storage media having instructions stored thereon that, when executed by one or more processors (Memory, instructions, processors, see p129, p39-40, Vazquez), cause the one or more processors to:
store a digital twin on the one or more storage media (An architecture inference engine, which is interpreted as a digital twin for a building system, can be stored in database storage, and is comprised of individual digital twins for components of the specified building system, see Fig. 9, Fig, 6, p82, p100, p82, p7, p104-105, Vazquez), the digital twin including one or more fault detection or diagnostics functions (Architecture includes fault diagnoses, see p57, p82, p104, p7, p80, Fig. 6, Fig. 9, Vazquez) and a virtual representation of a first piece of building equipment (Equipment represented virtually by digital twins, for example first device such as an air handling unit AHU, p101, Fig. 9, p100, Vazquez) and a second piece of building equipment related to the first piece of building equipment (Equipment represented virtually by digital twins, for example a second device such as a valve VAV1 that is related to a first piece of equipment such as an AHU by operation and/or by a fault cause and effect, see p51-52, p101, Fig. 9, p100, p104, p66, 75, Vazquez), the virtual representation comprising a building graph including nodes representing one or more entities of a building and edges between the nodes representing relationships between the one or more entities of the building (Representation that is graph style with nodes representative of specific system equipment components, and edges illustrative of a relation between different components, see Fig. 9, p100-P101, Fig, 6, p82, p82, p7, p104-105, Vazquez), wherein the one or more fault detection or diagnostic functions operate on the virtual representation of the first piece of building equipment to perform fault detection or diagnostics (Architecture inference engine includes fault diagnoses operated on component digital twin representations with Bayesian networks , such as a first component, see p7, p80, Fig. 6, Fig. 9, p57, p82, p104, Vazquez);
execute the digital twin based on the virtual representation of the first piece of building equipment to generate an indication of a fault or a diagnosis of the fault for the first piece of building equipment (Execution for fault diagnoses operated on component digital twin representations, such as a first component, see Abs., p7, p80, p57, p82, p104, p7, p80, Fig. 6, Fig. 9, Vazquez);
store an indication of the fault or a diagnosis of the fault, or a link to the fault or the diagnosis of the fault, in the virtual representation of the first piece of building equipment by adding the indication of the fault or the diagnosis of the fault, or the link to the fault or the diagnosis of the fault to an existing node in the building graph or creating a new node in the building graph with the indication of the fault or the diagnosis of the fault, or the link to the fault or the diagnosis of the fault (Faults are stored and as indications on virtual digital twin representations, and added with edge links, see Fig. 9, p82, p7, p102, Fig. 6, p80, p57, p82, p104, p7, Vazquez);
Vazquez does not explicitly teach perform an automated action using a second piece of equipment related to a first piece of equipment by a digital twin in response to an indication of a fault or diagnosis of the fault.
However, Mehrotra from the same or similar field of digital twins, teaches perform an automated action using a second piece of equipment related to a first piece of equipment by a digital twin in response to an indication of a fault or diagnosis of the fault (Upon an issue (i.e. fault) determined on a first piece of equipment that can be of a building, such as a factory building, an automation action can be performed using a second piece associated with the first piece. For example, a motor equipment with digital twin can be used to identify an anomaly, and a automation controller associated with motor can perform an action, where controllers and program can also have representations, or associated devices can be simulated via digital twins to determine anomalies, and perform automation simulations with the coordinated assets on updated parameters, see p177, 40-42, 185, 45, 51 , 93, 28-29, 150, 175, 180, Mehrotra).
It would have been obvious to a person of ordinary skill in the art before the filing date of the claimed invention to modify the digital twin and fault detection as described by Vazquez and incorporating performing an action by a related device in response to a fault, as taught by Mehrotra
One of ordinary skill in the art would have been motivated to do this modification in order to better address a potential issue in a system by coordinating a response by assets that are interrelated (see p177, 40-42, 185, 45, 51 , 93, 150, 175, 180, 28-29, Mehrotra).
Regarding claim 2, the combination of Vazquez and Mehrotra teaches all the limitations of the base claim as outlined above, and are analyzed as previously discussed with regard to that claim.
Vazquez further teaches wherein the virtual representation of the one or more pieces of building equipment includes a building graph comprising a plurality of nodes representing a plurality of entities of the building and a plurality of edges between the plurality of nodes representing relationships between the plurality of entities of the building (Representation that is graph style with nodes representative of specific system equipment components, and edges illustrative of a relation between different components, see Fig. 9, p100-P101, Fig, 6, p82, p82, p7, p104-105, Vazquez).
Regarding claim 12, the combination of Vazquez and Mehrotra teaches all the limitations of the base claim as outlined above, and are analyzed as previously discussed with regard to that claim.
Vazquez further teaches wherein instructions further cause one or more processors to receive an indication to: receive an indication that a fault has been detected in a digital twin (Fault detection and with inference engine that uses digital twin, see p72, 77, 93, 100-101, p80, Vazquez); and execute a second digital twin, the second digital twin including one or more fault detection or diagnostics functions and a second virtual representation of the second piece of building equipment, the second virtual representation including one or more second entities of a building and relationships between at least one of the second entities of the building and at least one of the entities of the building, wherein the one or more fault detection or diagnostic functions of the second digital twin operate on the second virtual representation of the first piece of building equipment to perform fault detection or diagnostics based on a determination of the fault detected in the digital twin (Fault detection and with inference engine that uses digital twins for multiple components and relationships, thus a second digital twin representation with fault diagnostics, see p72, 77, 93, 100-101, p80, Fig. 9, Fig 6,Vazquez).
Claim 14 is rejected on the same grounds as claims 1.
Claim 18 is rejected on the same grounds as claim 14.
Claims 3, 4, 5, 7, 15, 16, 19, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Vazquez, in view of Mehrotra, and in further view of US Patent Publication No. 2016/0203036 to Mezic et al., (hereinafter Mezic).
Regarding claim 3, the combination of Vazquez and Mehrotra teaches all the limitations of the base claim as outlined above, and are analyzed as previously discussed with regard to that claim.
Vazquez further teaches wherein the one or more fault detection or diagnostics functions include a fault rule (Fault determination rules can be used, see p57, Vazquez) wherein the one or more fault detection or diagnostics functions include a fault rule including a threshold, wherein the threshold being met indicates the fault or a diagnosis for the fault.
Vazquez does not explicitly teach wherein one or more fault detection or diagnostics functions include a fault rule including a threshold, wherein the threshold being met indicates the fault or a diagnosis for the fault.
However, Mezic from the same or similar field of building systems and fault determinations, teaches wherein one or more fault detection or diagnostics functions include a fault rule including a threshold, wherein the threshold being met indicates the fault or a diagnosis for the fault (A threshold used to determine an anomalous fault condition, see P50, P14, P27-28, Mezic).
It would have been obvious to a person of ordinary skill in the art before the filing date of the claimed invention to modify the digital twin and fault detection as described by the combination that includes Vazquez and incorporating use of threshold, as taught by Mezic
One of ordinary skill in the art would have been motivated to do this modification in order to better simplify fault determination by using a desired limit of acceptable quantified operational values (see P50, P14, P27-28, Mezic).
Regarding claim 4, the combination of Vazquez, Mehrotra, and Mezic teaches all the limitations of the base claim as outlined above, and are analyzed as previously discussed with regard to that claim.
Mezic further teaches wherein the instructions further cause the one or more processors to: receive a state of the first piece of building equipment (Data and conditions of devices received, including fault, setpoints, sensed conditions, etc., which can include from a device characterized as a first piece, see P48, P50, P44, Mezic); assess, using a machine learning model, a determination of whether the first piece of building equipment has the fault is a false positive or a false negative based on the state and the threshold (Machine learning system used in determining whether a fault has actually occurred or not based on a fault state determination using thresholds, see P55, P50, P14, P27-28, Mezic); determine a new threshold based on the assessment of the machine learning model (Machine learning determines the need for modification of fault detection that uses thresholds based on feedback assessment, see P55, P50, 52, P14, P27-28, Mezic); and replace the threshold with the new threshold to make subsequent determinations of whether the first piece of building equipment or other building equipment has a fault (Machine learning modifies fault detection that uses thresholds based on feedback assessment for upcoming incidents, see P55, P50-52, P14, P27-28, Mezic).
It would have been obvious to a person of ordinary skill in the art before the filing date of the claimed invention to modify the digital twin and fault detection as described by the combination that includes Vazquez and incorporating false positive or negative, and replacement of a threshold, as taught by Mezic
One of ordinary skill in the art would have been motivated to do this modification in order to better maintain appropriate limit of a defined operation that minimizes erroneous fault detections (see P55, P50-52, P14, P27-28, Mezic).
Regarding claim 5, the combination of Vazquez, Mehrotra, and Mezic teaches all the limitations of the base claim as outlined above, and are analyzed as previously discussed with regard to that claim.
Mezic further teaches wherein the new threshold reduces a number of false positives a number of false negatives (Remove false positives, see P8, P55, P50-52, P14, P27-28, Mezic).
It would have been obvious to a person of ordinary skill in the art before the filing date of the claimed invention to modify the digital twin and fault detection as described by the combination that includes Vazquez and incorporating reduction of false positives or negatives, as taught by Mezic
One of ordinary skill in the art would have been motivated to do this modification in order to better minimize waste of time that can be caused by analyzing a misdiagnosed fault (see P8, P55, P50-52, P14, P27-28, Mezic).
Regarding claim 7, the combination of Vazquez, Mehrotra, and Mezic teaches all the limitations of the base claim as outlined above, and are analyzed as previously discussed with regard to that claim.
Mezic further teaches wherein the fault rule includes: a condition portion including a comparison of the state to the threshold (Comparison made between a condition, such as obtained from sensors or scored value condition, and a threshold, see P27-29, P50- 52, P44, 48, P14, Mezic); and an action portion including a determination that the building equipment is faulty when the condition is satisfied or not faulty when the condition is not satisfied (Determination of fault or abnormality is made, see P27-29, P50- 52, P44, 48, P14, Mezic).
It would have been obvious to a person of ordinary skill in the art before the filing date of the claimed invention to modify the digital twin and fault detection as described by the combination that includes Vazquez and incorporating a rule with threshold comparison and fault determination, as taught by Mezic
One of ordinary skill in the art would have been motivated to do this modification in order to better simplify fault determination by using a desired limit of acceptable quantified operational values and determining fault based on a limit being exceeded (see P27-29, P50- 52, P44, 48, P14, p8, P55, P50-52, P14, P27-28, Mezic).
Claim 15 is rejected on the same grounds as claims 2 and 3.
Claim 16 is rejected on the same grounds as claim 4.
Claim 19 is rejected on the same grounds as claims 15.
Claim 20 is rejected on the same grounds as claims 16.
Claims 6, 13, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Vazquez, in view of Mehrotra, in further view of Mezic, and in further view of US Patent Publication No. 2022/0156154 to Varnavas et al., (hereinafter Varnavas)
Regarding claim 6, the combination of Vazquez, Mehrotra, and Mezic teaches all the limitations of the base claim as outlined above, and are analyzed as previously discussed with regard to that claim.
Vazquez further teaches accumulating data via a machine learning system (Machine learning system, see P108, Vazquez)
Vazquez does not explicitly teach wherein instructions further cause one or more processors to accumulate training data for a machine learning model using a state and a threshold as inputs and labels of false positive or false negative as outputs.
However, Varnavas from the same or similar field of anomaly fault determination with machine learning, teaches wherein instructions further cause one or more processors to accumulate training data for a machine learning model using a state and a threshold as inputs and labels of false positive or false negative as outputs (Data is accumulated as a result of state operational data and threshold inputs used by machine learning used to determine fault occurrences. The accumulated signal data is used on feeding training data for a model, and data is labeled by the machine learning system as indicative of whether fault is accurately predicted or not (i.e. false determination or not), see P155, 152-3, Varnavas).
It would have been obvious to a person of ordinary skill in the art before the filing date of the claimed invention to modify the digital twin and fault detection as described by the combination that includes Vazquez and incorporating training of machine learning, as taught by Varnavas
One of ordinary skill in the art would have been motivated to do this modification in order to better improve a machine learning model so as to adapt to better adjust to provide improved fault predictions based on feedback and training using relevant data (see P155, Varnavas).
Regarding claim 13, the combination of Vazquez and Mehrotra teaches all the limitations of the base claim as outlined above, and are analyzed as previously discussed with regard to that claim.
Vazquez further teaches wherein instructions further cause one or more processors to receive an indication to: execute a fault detection and diagnostics (FDD) agent and machine learning (Fault detection and Machine learning system, see P108, p72, 77, 93, 100-101, p80, Vazquez)
Vazquez does not explicitly teach an agent including one or more machine learning models for determining a new threshold in a fault rule for determining whether a building equipment has a fault; and providing training data to machine learning model, wherein the training data includes a plurality of states and a plurality of thresholds of the fault rule as inputs and feedbacks of false positive and false negative of the fault rule as outputs.
However, Mezic from the same or similar field of building systems and fault determinations, teaches an agent including one or more machine learning models for determining a new threshold in a fault rule for determining whether building equipment has a fault (Machine learning executes a determination that leads to a need for modification of fault detection that uses thresholds (i.e. rule) used in building equipment fault assessment, see P55, P50, 52, P14, P27-28, Mezic);
It would have been obvious to a person of ordinary skill in the art before the filing date of the claimed invention to modify the digital twin and fault detection as described by the combination that includes Vazquez and incorporating determination of new threshold, as taught by Mezic
One of ordinary skill in the art would have been motivated to do this modification in order to better maintain appropriate limit of a defined operation that minimizes erroneous fault detections (see P55, P50-52, P14, P27-28, Mezic).
Vazques does not explicitly teach providing training data to a machine learning model, wherein the training data includes a plurality of states and plurality of thresholds of a fault rule as inputs and feedbacks of false positive or false negative of a fault rule as outputs.
However, Varnavas from the same or similar field of anomaly fault determination with machine learning, teaches providing training data to a machine learning model, wherein the training data includes a plurality of states and plurality of thresholds of a fault rule as inputs and feedbacks of false positive or false negative of a fault rule as outputs (Data is accumulated as a result of state operational data and threshold inputs used by machine learning used to determine fault occurrences. The data is used on feeding feedback training data for a model, and data is labeled by the machine learning system as indicative of whether fault is accurately predicted or not (i.e. false determination or not), see P155, 152-3, Varnavas).
It would have been obvious to a person of ordinary skill in the art before the filing date of the claimed invention to modify the machine learning fault detection as described by the combination that includes Vazquez and incorporating training of machine learning, as taught by Varnavas
One of ordinary skill in the art would have been motivated to do this modification in order to better improve a machine learning model so as to adapt to better adjust to provide improved fault predictions based on feedback and training using relevant data (see P155, Varnavas).
Regarding claim 17, the combination of Vazquez and Mehrotra teaches all the limitations of the base claim as outlined above, and are analyzed as previously discussed with regard to that claim.
Vazquez does not explicitly teach accumulating, by a processing circuit, training data for a machine learning model using a state and a threshold as inputs and labels of false positive or false negative as outputs, wherein a new threshold reduces a number of false positives a number of false negatives.
However, Mezic from the same or similar field of building systems and fault determinations, teaches wherein a new threshold reduces a number of false positives a number of false negatives (Remove false positives, see P8, P55, P50-52, P14, P27-28, Mezic).
It would have been obvious to a person of ordinary skill in the art before the filing date of the claimed invention to modify the digital twin and fault detection as described by the combination that includes Vazquez and incorporating reduction of false positives or negatives, as taught by Mezic
One of ordinary skill in the art would have been motivated to do this modification in order to better minimize waste of time that can be caused by analyzing a misdiagnosed fault (see P8, P55, P50-52, P14, P27-28, Mezic).
Vazquez does not explicitly teach accumulating, by a processing circuit, training data for a machine learning model using a state and a threshold as inputs and labels of false positive or false negative as outputs.
However, Varnavas from the same or similar field of anomaly fault determination with machine learning, teaches accumulating, by a processing circuit, training data for a machine learning model using a state and a threshold as inputs and labels of false positive or false negative as output (Data is accumulated as a result of state operational data and threshold inputs used by machine learning used to determine fault occurrences. The accumulated signal data is used on feeding training data for a model, and data is labeled by the machine learning system as indicative of whether fault is accurately predicted or not (i.e. false determination or not), see P155, 152-3, Varnavas).
It would have been obvious to a person of ordinary skill in the art before the filing date of the claimed invention to modify the machine learning fault detection as described by the combination that includes Vazquez and incorporating training of machine learning, as taught by Varnavas
One of ordinary skill in the art would have been motivated to do this modification in order to better improve a machine learning model so as to adapt to better adjust to provide improved fault predictions based on feedback and training using relevant data (see P155, Varnavas).
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Vazquez, in view of Mehrotra, in further view of Mezic, and in further view of US Patent Publication No. 2015/0379429 to Lee et al., (hereinafter Lee).
Regarding claim 8, the combination of Vazquez, Mehrotra, and Mezic teaches all the limitations of the base claim as outlined above, and are analyzed as previously discussed with regard to that claim.
Vazquez further teaches instructions to cause one or more processors to control a building equipment (Building components controlled such as by setpoints, see P51-52, Vazquez)
Vazquez does not explicitly teach to perturb a system with multiple values of a threshold to provide additional data for a machine learning model.
However, Lee from the same or similar field of machine learning based evaluation models, teaches to perturb a system with multiple values of a threshold to provide additional data for a machine learning model (A system can be evaluated under different scenarios including thresholds to provide data regarding machine learning model, see P308, P251, Lee).
It would have been obvious to a person of ordinary skill in the art before the filing date of the claimed invention to modify the machine learning fault detection as described by the combination that includes Vazquez and incorporating perturbing to obtain additional data, as taught by Lee.
One of ordinary skill in the art would have been motivated to do this modification in order to better asses and improve the performance of machine learning by changing and observing the effect of various scenarios to see how the machine learning functions to asses objective and accuracy and adjust as needed (see P308, P251, 307-313 ,Lee).
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Vazquez in view of Mehrotra, in further view of Mezic, and in further view of US Patent Publication No. 2021/0344695 to Palani et al., (hereinafter Palani).
Regarding claim 9, the combination of Vazquez, Mehrotra, and Mezic teaches all the limitations of the base claim as outlined above, and are analyzed as previously discussed with regard to that claim.
While learning models are implied by Vazquez (see p108) by use of machine learning, Vazquez does not explicitly teach wherein a machine learning model includes a first machine learning model for predicting a false negative and a second machine learning model for predicting a false positive.
However, Palani from the same or similar field of anomaly fault determination with machine learning, teaches wherein a machine learning model includes a first machine learning model for predicting a false negative and a second machine learning model for predicting a false positive (Respective models utilized wherein one model can predict a false positive and another a false negative, see P39, P20, Palani).
It would have been obvious to a person of ordinary skill in the art before the filing date of the claimed invention to modify the machine learning fault detection as described by the combination that includes Vazquez and incorporating machine learning models, as taught by Palani
One of ordinary skill in the art would have been motivated to do this modification in order to better improve determination and differentiation of anomalous predictions by assessment of various models see P39, P20, Palani).
Claims 10 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Vazquez, in view of Mehrotra, in further view of Mezic, in further view of Palani, and in further view of Varnavas.
Regarding claim 10, the combination of Vazquez, Mehrotra, Mezic, and Palani teaches all the limitations of the base claim as outlined above, and are analyzed as previously discussed with regard to that claim.
Palani further teaches wherein the first machine learning model is configured to accurately
predict false positives (Models utilized wherein a model can predict a false positive at an accuracy, see P39, P20, Palani).
It would have been obvious to a person of ordinary skill in the art before the filing date of the claimed invention to modify the machine learning fault detection as described by the combination that includes Vazquez and incorporating machine learning models for predicting false results, as taught by Palani
One of ordinary skill in the art would have been motivated to do this modification in order to better improve determination and differentiation of anomalous predictions by assessment of a model (see P39, P20, Palani).
Vazquez does not explicitly teach different values of state and threshold, and wherein instructions further cause one or more processors to retrain a machine learning model.
However, Varnavas from the same or similar field of anomaly fault determination with machine learning, teaches different values of state and threshold, and wherein instructions further cause one or more processors to retrain a machine learning model (Data is accumulated as a result of state operational data and threshold inputs used by machine learning used to determine fault occurrences. The data is used on feeding feedback training (i.e. retraining) data for a model, and data is labeled by the machine learning system as indicative of whether fault is accurately predicted or not (i.e. false determination or not), see P155, 152-3, Varnavas).
It would have been obvious to a person of ordinary skill in the art before the filing date of the claimed invention to modify the machine learning fault detection as described by the combination that includes Vazquez and incorporating training of machine learning on different data, as taught by Varnavas
One of ordinary skill in the art would have been motivated to do this modification in order to better improve a machine learning model so as to adapt to better adjust to provide improved fault predictions based on feedback and training using relevant data (see P155, Varnavas).
Regarding claim 11, the combination of Vazquez, Mehrotra, Mezic, and Palani teaches all the limitations of the base claim as outlined above, and are analyzed as previously discussed with regard to that claim.
Palani further teaches wherein the first machine learning model is configured to accurately
predict negatives positives (Models (i.e. first or second model) utilized, wherein a model can predict a false negatives at an accuracy, see P39, P20, Palani).
It would have been obvious to a person of ordinary skill in the art before the filing date of the claimed invention to modify the machine learning fault detection as described by the combination that includes Vazquez and incorporating machine learning models for predicting false results, as taught by Palani
One of ordinary skill in the art would have been motivated to do this modification in order to better improve determination and differentiation of anomalous predictions by assessment of a model (see P39, P20, Palani).
Vazquez does not explicitly teach different values of state and threshold, and wherein instructions further cause one or more processors to retrain a machine learning model.
However, Varnavas from the same or similar field of anomaly fault determination with machine learning, teaches different values of state and threshold, and wherein instructions further cause one or more processors to retrain a machine learning model (Data is accumulated as a result of state operational data and threshold inputs used by machine learning used to determine fault occurrences. The data is used on feeding feedback training (i.e. retrainng) data for a model, and data is labeled by the machine learning system as indicative of whether fault is accurately predicted or not (i.e. false determination or not), see P155, 152-3, Varnavas).
It would have been obvious to a person of ordinary skill in the art before the filing date of the claimed invention to modify the machine learning fault detection as described by the combination that includes Vazquez and incorporating training of machine learning on different data, as taught by Varnavas
One of ordinary skill in the art would have been motivated to do this modification in order to better improve a machine learning model so as to adapt to better adjust to provide improved fault predictions based on feedback and training using relevant data (see P155, Varnavas).
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Kallus et al., US. Patent Publication No. 2023/0213920 teaches continuous training loop of RL agents of sensor control system a digital twin of a process graph employed with measured state information for given scenarios and for updating the model when needed.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to EMILIO J SAAVEDRA whose telephone number is (571)270-5617. The examiner can normally be reached M-F: 9:30am-5:30pm (EST).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Robert E Fennema can be reached at (571) 272-2748. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/EMILIO J SAAVEDRA/Primary Patent Examiner, Art Unit 2117